All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 302,623
- 12,610
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 1,393–1,416 of 302,623 skills
- 629 Faq 41b03e5d**Got questions?** You're not alone! Here are answers to the most common questions about Antigravity Awesome Skills. ---Votes: 0GitHub stars: 9
- 629 Faq 39d26d09OpenViking is an open-source context database designed specifically for AI Agents. It solves core pain points when building AI Agents:Votes: 0GitHub stars: 9
- 629 Faq 3917033aOpenViking is an open-source context database designed specifically for AI Agents. It solves core pain points when building AI Agents:Votes: 0GitHub stars: 9
- 629 Faq 35c56a80OpenViking 是一个专为 AI Agent 设计的开源上下文数据库。它解决了构建 AI Agent 时的核心痛点：Votes: 0GitHub stars: 9
- 629 Faq 334f5eccOpenViking is an open-source context database designed specifically for AI Agents. It solves core pain points when building AI Agents:Votes: 0GitHub stars: 9
- 629 Faq 256da4b2**Got questions?** You're not alone! Here are answers to the most common questions about Antigravity Awesome Skills. ---Votes: 0GitHub stars: 9
- 629 Faq 1dfa4d66OpenViking 是一个专为 AI Agent 设计的开源上下文数据库。它解决了构建 AI Agent 时的核心痛点：Votes: 0GitHub stars: 9
- 621 Extending 0ef2e36fThis guide explains how to extend Local Deep Research with custom components.Votes: 0GitHub stars: 9
- 375 Ranking Bff3fc0fSkyll uses a multi-signal ranking algorithm to order search results by relevance. Each skill receives a score from 0-100 based on weighted factors, with a small additional boost for curated registry skills.Votes: 0GitHub stars: 9
- 374 References 8157973f> **Created:** 2025-11-28 > **Purpose:** Reference collection for Claude Code Skills related to Python specifications and best practices ---Votes: 0GitHub stars: 9
- 344 Execution Execute Ticket 89111d7fImplement a ticket by following its self-contained implementation details: write code, create tests, verify acceptance criteria. ---Votes: 0GitHub stars: 9
- 338 Supported Agents E950f36fThis plugin follows the [Agent Skills specification](https://agentskills.io/specification), an open standard for packaging reusable AI agent capabilities. Skills are portable across any agent that implements the spec.Votes: 0GitHub stars: 9
- 338 Supported Agents 03117728This plugin follows the [Agent Skills specification](https://agentskills.io/specification), an open standard for packaging reusable AI agent capabilities. Skills are portable across any agent that implements the spec.Votes: 0GitHub stars: 9
- 320 Client Injection E2d87047On Letta Cloud, tools have access to a pre-injected `client` variable and environment variables. This enables powerful patterns like custom memory tools.Votes: 0GitHub stars: 9
- 300 Agent Loop D8761318This document maps the main agent loop and orchestration architecture in tunacode.Votes: 0GitHub stars: 9
- 300 Agent Loop 3dceda65This document maps the main agent loop and orchestration architecture in tunacode.Votes: 0GitHub stars: 9
- 283 Openai 75ee5c2a[OpenAI](https://platform.openai.com/docs/overview) is an AI research and deployment company that provides a suite of powerful language models. The Strands Agents SDK implements an OpenAI provider, allowing you to run agents against any OpenAI or OpenAI-compatible model.Votes: 0GitHub stars: 9
- 282 Agent Config Ee9b6cf0{{ experimental_feature_warning() }} The experimental `config_to_agent` function provides a simple way to create agents from configuration files or dictionaries.Votes: 0GitHub stars: 9
- 281 Agent 6246197a{{ experimental_feature_warning() }} The `BidiAgent` is a specialized agent designed for real-time bidirectional streaming conversations. Unlike the standard `Agent` that follows a request-response pattern, `BidiAgent` maintains persistent connections that enable continuous audio and text streaming, real-time interruptions, and concurrent tool execution. ```mermaid flowchart TB subgraph User A[Microphone] --> B[Audio Input] C[Text Input] --> D[Input Events] B --> D end subgraph BidiAgent D --...Votes: 0GitHub stars: 9
- 280 State 6969f13dStrands Agents state is maintained in several forms: 1. **Conversation History:** The sequence of messages between the user and the agent. 2. **Agent State**: Stateful information outside of conversation context, maintained across multiple requests. 3. **Request State**: Contextual information maintained within a single request. Understanding how state works in Strands is essential for building agents that can maintain context across multi-turn interactions and workflows.Votes: 0GitHub stars: 9
- 279 Retry Strategies D0f56e64Model providers occasionally encounter errors such as rate limits, service unavailability, or network timeouts. By default, the agent retries `ModelThrottledException` failures automatically with exponential backoff and the `Angent.retry_strategy` parameter lets you customize this behavior.Votes: 0GitHub stars: 9
- 279 Retry Strategies C90df465Model providers occasionally encounter errors such as rate limits, service unavailability, or network timeouts. By default, the agent retries `ModelThrottledException` failures automatically with exponential backoff and the `Angent.retry_strategy` parameter lets you customize this behavior.Votes: 0GitHub stars: 9
- 277 Conversation Management 2d7edb45In the Strands Agents SDK, context refers to the information provided to the agent for understanding and reasoning. This includes: - User messages - Agent responses - Tool usage and results - System prompts As conversations grow, managing this context becomes increasingly important for several reasons: 1. **Token Limits**: Language models have fixed context windows (maximum tokens they can process) 2. **Performance**: Larger contexts require more processing time and resources 3. **Relevance**...Votes: 0GitHub stars: 9
- 274 Python 105c1d10@tool def letter_counter(word: str, letter: str) -> int: """ Count occurrences of a specific letter in a word. Args: word (str): The input word to search in letter (str): The specific letter to count Returns: int: The number of occurrences of the letter in the word """ if not isinstance(word, str) or not isinstance(letter, str): return 0 if len(letter) != 1: raise ValueError("The 'letter' parameter must be a single character") return word.lower().count(letter.lower()) agent = Agent(tools=[cal...Votes: 0GitHub stars: 9